It is ecommerce based recommendation engine built on operational data one of the ecommerce application. It uses the hybrid approach to recommend products. Hybrid approach combines both attribute of user, items to solve the problem of cold start and data sparsity. User attributes: Age, Gender and Items attributes: Price, Brand, Category has been considered along with interaction's purchase, click, wishlist to built model

• Flask
• Python
• Streamlit
• Postgresql

1. Install Dependencies
2. Run API
3. Run Frontend

1. Create a virtual environment with python3

   python3 -m virtualenv venv

2. Activate the virtual environment:

   cd venv
   source /bin/activate

3. Install dependencies

   pip install -r requirements.txt

1. Configure the database Create database and add .env file in api/.env. template of .env is as follows:

   DATABASE_NAME =
   DATABASE_PORT =
   USER_NAME =
   USER_PASSWORD =

2. Navigate to root of the project
3. Set environment variables

   export FLASK_APP=app:create_app
   export APP_SETTINGS="api.config.DevelopmentConfig"

4. Run Flask

   flask run

1. Run streamlit application as:

   streamlit run streamlit_app.py